| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Acre. |
|
Data corrente: |
21/12/2022 |
|
Data da última atualização: |
21/12/2022 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Autoria: |
VERAS, H. F. P.; FERREIRA, M. P.; CUNHA NETO, E. M. da; FIGUEIREDO, E. O.; DALLA CORTE, A. P.; SANQUETTA, C. R. |
|
Afiliação: |
HUDSON FRANKLIN PESSOA VERAS, UNIVERSIDADE FEDERAL DO PARANÁ; MATHEUS PINHEIRO FERREIRA, INSTITUTO MILITAR DE ENGENHARIA; ERNANDES MACEDO DA CUNHA NETO, UNIVERSIDADE FEDERAL DO PARANÁ; EVANDRO ORFANO FIGUEIREDO, CPAF-AC; ANA PAULA DALLA CORTE, UNIVERSIDADE FEDERAL DO PARANÁ; CARLOS ROBERTO SANQUETTA, UNIVERSIDADE FEDERAL DO PARANÁ. |
|
Título: |
Fusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests. |
|
Ano de publicação: |
2022 |
|
Fonte/Imprenta: |
Ecological Informatics, v. 71, 101815, 2022. |
|
ISSN: |
1574-9541 |
|
DOI: |
https://doi.org/10.1016/j.ecoinf.2022.101815 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Remote sensing images obtained by unoccupied aircraft systems (UAS) across different seasons enabled capturing of species-specific phenological patterns of tropical trees. The application of UAS multi-season images to classify tropical tree species is still poorly understood. In this study, we used RGB images from different seasons obtained by a low-cost UAS and convolutional neural networks (CNNs) to map tree species in an Amazonian forest. Individual tree crowns (ITC) were outlined in the UAS images and identified to the species level using forest inventory data. The CNN model was trained with images obtained in February, May, August, and November. The classification accuracy in the rainy season (November and February) was higher than in the dry season (May and August). Fusing images from multiple seasons improved the average accuracy of tree species classification by up to 21.1 percentage points, reaching 90.5%. The CNN model can learn species-specific phenological characteristics that impact the classification accuracy, such as leaf fall in the dry season, which highlights its potential to discriminate species in various conditions. We produced high-quality individual tree crown maps of the species using a post-processing procedure. The combination of multi-season UAS images and CNNs has the potential to map tree species in the Amazon, providing valuable insights for forest management and conservation initiatives. |
|
Palavras-Chave: |
Acre; Amazonia Occidental; Amazônia Ocidental; Bosques experimentales; Bosques tropicales; Embrapa Acre; Fusão de imagens; Identificación de especies; Imagem multitemporada; Imagem RGB; Mapeamento de espécies; Modelo CNN; Rio Branco (AC); Teledetección; Western Amazon. |
|
Thesagro: |
Campo Experimental; Espécie Nativa; Fenologia; Floresta Tropical; Identificação; Sensoriamento Remoto. |
|
Thesaurus Nal: |
Experimental forests; Phenology; Remote sensing; Species identification; Tropical forests. |
|
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1150165/1/27406.pdf
|
|
Marc: |
LEADER 02966naa a2200517 a 4500
001 2150165
005 2022-12-21
008 2022 bl uuuu u00u1 u #d
022 $a1574-9541
024 7 $ahttps://doi.org/10.1016/j.ecoinf.2022.101815$2DOI
100 1 $aVERAS, H. F. P.
245 $aFusing multi-season UAS images with convolutional neural networks to map tree species in Amazonian forests.$h[electronic resource]
260 $c2022
520 $aRemote sensing images obtained by unoccupied aircraft systems (UAS) across different seasons enabled capturing of species-specific phenological patterns of tropical trees. The application of UAS multi-season images to classify tropical tree species is still poorly understood. In this study, we used RGB images from different seasons obtained by a low-cost UAS and convolutional neural networks (CNNs) to map tree species in an Amazonian forest. Individual tree crowns (ITC) were outlined in the UAS images and identified to the species level using forest inventory data. The CNN model was trained with images obtained in February, May, August, and November. The classification accuracy in the rainy season (November and February) was higher than in the dry season (May and August). Fusing images from multiple seasons improved the average accuracy of tree species classification by up to 21.1 percentage points, reaching 90.5%. The CNN model can learn species-specific phenological characteristics that impact the classification accuracy, such as leaf fall in the dry season, which highlights its potential to discriminate species in various conditions. We produced high-quality individual tree crown maps of the species using a post-processing procedure. The combination of multi-season UAS images and CNNs has the potential to map tree species in the Amazon, providing valuable insights for forest management and conservation initiatives.
650 $aExperimental forests
650 $aPhenology
650 $aRemote sensing
650 $aSpecies identification
650 $aTropical forests
650 $aCampo Experimental
650 $aEspécie Nativa
650 $aFenologia
650 $aFloresta Tropical
650 $aIdentificação
650 $aSensoriamento Remoto
653 $aAcre
653 $aAmazonia Occidental
653 $aAmazônia Ocidental
653 $aBosques experimentales
653 $aBosques tropicales
653 $aEmbrapa Acre
653 $aFusão de imagens
653 $aIdentificación de especies
653 $aImagem multitemporada
653 $aImagem RGB
653 $aMapeamento de espécies
653 $aModelo CNN
653 $aRio Branco (AC)
653 $aTeledetección
653 $aWestern Amazon
700 1 $aFERREIRA, M. P.
700 1 $aCUNHA NETO, E. M. da
700 1 $aFIGUEIREDO, E. O.
700 1 $aDALLA CORTE, A. P.
700 1 $aSANQUETTA, C. R.
773 $tEcological Informatics$gv. 71, 101815, 2022.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Acre (CPAF-AC) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
|
| Registros recuperados : 1 | |
| Registros recuperados : 1 | |
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
